A method for generating a musical composition based on user input is described. A first set of musical characteristics is extracted from a first input musical piece. The first set of music characteristics is prepared as an input vector into an unsupervised neural net comprised of a plurality of computing layers by perturbing the first set of musical characteristics according to a user intent expressed in the user input to create a perturbed vector. The perturbed vector is input into the first set of nodes of the unsupervised neural net. The unsupervised neural net is operated to calculate an output vector from a highest set of nodes. The output vector is used to create an output musical piece.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for generating a musical composition based on user input, comprising: responsive to user input, extracting a first set of musical characteristics from a first input musical piece; preparing the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, wherein the input vector is prepared by perturbing the first set of musical characteristics according to a user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
A method for generating music based on user input. First, the system extracts musical features (like tempo, key, or melody) from an existing song chosen by the user. These features are then converted into a numerical vector, which serves as input to an unsupervised neural network containing multiple layers. Before feeding the vector into the network, the system modifies the vector based on user-specified preferences, such as mood (happy, sad), genre (jazz, classical), or intended activity (workout, relaxation). This modification creates a "perturbed" input vector. The neural network processes this vector to produce an output vector. Finally, the system uses the output vector to generate a new musical piece.
2. The method as recited in claim 1 , wherein the plurality of computing layers comprise a plurality of Restricted Boltzmann Machines (RBM).
The music generation method described above uses a specific type of unsupervised neural network called a Restricted Boltzmann Machine (RBM). The unsupervised neural network has multiple computing layers and each layer is composed of a set of nodes, wherein the input vector is prepared by perturbing the first set of musical characteristics according to a user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
3. The method as recited in claim 1 , wherein the user intent is selected from the group consisting of a mood, a genre of music and an activity to be performed while listening to the output musical piece.
In the music generation method, the user provides their "intent" to influence the output music. This intent can be a mood (e.g., happy, sad), a music genre (e.g., jazz, classical, rock), or an activity for which the music is intended (e.g., studying, exercising, sleeping). The system extracts a first set of musical characteristics from a first input musical piece; preparing the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
4. The method as recited in claim 2 , wherein a rule directs a selection of a set of pitches from a key signature associated with the user intent.
The music generation method, which uses Restricted Boltzmann Machines (RBMs) for its neural network layers, incorporates musical key signatures associated with the user's chosen intent (mood, genre, etc.). A rule is used to select specific pitches (notes) from the key signature and these pitches are used in generating the music. The system extracts a first set of musical characteristics from a first input musical piece; preparing the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
5. The method as recited in claim 1 , wherein the perturbing includes inserting random values into respective ones of the first set of nodes in the first visible layer.
As part of the music generation method, the "perturbing" step involves injecting random values into the first layer of the neural network. Specifically, random numbers are inserted into some or all of the nodes representing the musical characteristics extracted from the input song. The system extracts a first set of musical characteristics from a first input musical piece; preparing the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
6. The method as recited in claim 1 , further comprising: responsive to user input, extracting a second set of musical characteristics from a second input musical piece; inputting the second set of musical characteristics together with the first set of musical characteristics as the input vector into the first set of nodes in the first visible layer of the unsupervised neural net; and wherein the perturbed input vector is changed so that the first input musical piece has a greater effect on the output musical piece than the second input musical piece.
The music generation method can use two input songs. Musical characteristics are extracted from both songs and combined into a single input vector for the neural network. The "perturbing" step, where the input vector is modified according to user intent, is adjusted to ensure the first song has a greater influence on the final output than the second song. The system extracts a first set of musical characteristics from a first input musical piece; preparing the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
7. An apparatus, comprising: a processor; computer memory holding computer program instructions executed by the processor for generating a musical composition based on user input, the computer program instructions comprising: program code operative to extract a first set of musical characteristics from a first input musical piece; program code operative to prepare the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, wherein the input vector is prepared by perturbing the first set of musical characteristics according to a user intent expressed in the user input to create a perturbed input vector; program code operative to provide the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; program code operative to use the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes; and program code operative to use the output vector to create an output musical piece.
An apparatus (e.g., a computer or music synthesizer) generates music based on user input. The apparatus has a processor and memory storing instructions. The instructions, when executed, extract musical features from an input song, convert them into a vector, and feed it into an unsupervised neural network (multiple layers of computing nodes). The input vector is modified ("perturbed") based on user preferences like mood or genre. The neural network processes this vector and creates an output vector, which is then used to generate the final musical piece.
8. The apparatus as recited in claim 7 , wherein the plurality of computing layers comprise a plurality of Restricted Boltzmann Machines (RBM).
The music generation apparatus described above uses a specific type of unsupervised neural network called a Restricted Boltzmann Machine (RBM) within its computing layers. The computer program instructions executed by the processor extract a first set of musical characteristics from a first input musical piece; prepare the first set of musical characteristics as an input vector into the unsupervised neural net; perturb the input vector based on user intent to create a perturbed input vector; provide the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operate the unsupervised neural net using the perturbed input vector to calculate an output vector; and use the output vector to create an output musical piece.
9. The apparatus as recited in claim 7 , wherein the user intent is selected from the group consisting of a mood, a genre of music and an activity to be performed while listening to the output musical piece.
In the music generation apparatus, the user provides their "intent" to influence the output music. This intent can be a mood (e.g., happy, sad), a music genre (e.g., jazz, classical, rock), or an activity for which the music is intended (e.g., studying, exercising, sleeping). The computer program instructions executed by the processor extract a first set of musical characteristics from a first input musical piece; prepare the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; provide the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operate the unsupervised neural net using the perturbed input vector to calculate an output vector; and use the output vector to create an output musical piece.
10. The apparatus as recited in claim 7 , wherein the computer program instructions further comprise program code operative to direct a selection of rule to insert a set of pitches from a key signature associated with the user intent into the first visible layer.
The music generation apparatus includes instructions to select pitches from a key signature associated with the user's "intent" (mood, genre, etc.). A rule is used to select these pitches, which are then incorporated into the first layer of the neural network. The computer program instructions executed by the processor extract a first set of musical characteristics from a first input musical piece; prepare the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; provide the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operate the unsupervised neural net using the perturbed input vector to calculate an output vector; and use the output vector to create an output musical piece.
11. The apparatus as recited in claim 7 , wherein the computer program instructions further comprise: program code operative to extracting a second set of musical characteristics from a second input musical piece; program code operative to input the second set of musical characteristics together with the first set of musical characteristics as the input vector into the first set of nodes in the first visible layer of the unsupervised neural net; and program code operative to change the perturbed input vector so that the first input musical piece has a greater effect on the output musical piece than the second input musical piece.
The music generation apparatus can use two input songs. Musical characteristics are extracted from both songs and combined into a single input vector. The "perturbing" step (modifying the input based on user intent) is adjusted to ensure the first song has a greater influence on the final output than the second song. The computer program instructions executed by the processor extract a first set of musical characteristics from a first input musical piece; prepare the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; provide the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operate the unsupervised neural net using the perturbed input vector to calculate an output vector; and use the output vector to create an output musical piece.
12. A computer program product in a non-transitory computer readable medium for use in a data processing system, the computer program product holding computer program instructions which, when executed by the data processing system, for generating a musical composition based on user input, the computer program instructions comprising: program code operative to extract a first set of musical characteristics from a first input musical piece; program code operative to prepare the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, wherein the input vector is prepared by perturbing the first set of musical characteristics according to a user intent expressed in the user input to create a perturbed input vector; program code operative to provide the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; program code operative to use the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes; and program code operative to use the output vector to create an output musical piece.
A computer program, stored on a non-transitory medium, generates music based on user input. When executed, the program extracts musical features from an input song, converts them into a numerical vector, and feeds it into an unsupervised neural network (multiple layers of computing nodes). The input vector is modified ("perturbed") based on user preferences like mood or genre. The neural network processes this vector and creates an output vector, which is then used to generate the final musical piece.
13. The computer program product as recited in claim 12 , wherein the user intent is selected from the group consisting of a mood, a genre of music and an activity to be performed while listening to the output musical piece.
In the music generation computer program, the user provides their "intent" to influence the output music. This intent can be a mood (e.g., happy, sad), a music genre (e.g., jazz, classical, rock), or an activity for which the music is intended (e.g., studying, exercising, sleeping). The program extracts a first set of musical characteristics from a first input musical piece; prepares the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; provides the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operates the unsupervised neural net using the perturbed input vector to calculate an output vector; and uses the output vector to create an output musical piece.
14. The computer program product as recited in claim 12 , wherein the computer program instructions further comprise program code operative to direct a selection of rule to insert a set of pitches from a key signature associated with the user intent into the first visible layer.
The music generation computer program includes instructions to select pitches from a key signature associated with the user's "intent" (mood, genre, etc.). A rule is used to select these pitches, which are then incorporated into the first layer of the neural network. The program extracts a first set of musical characteristics from a first input musical piece; prepares the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; provides the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operates the unsupervised neural net using the perturbed input vector to calculate an output vector; and uses the output vector to create an output musical piece.
15. The computer program product as recited in claim 12 , wherein the computer program instructions further comprise: program code operative to extracting a second set of musical characteristics from a second input musical piece; program code operative to input the second set of musical characteristics together with the first set of musical characteristics as the input vector into the first set of nodes in the first visible layer of the unsupervised neural net; and program code operative to change the perturbed input vector so that the first input musical piece has a greater effect on the output musical piece than the second input musical piece.
The music generation computer program can use two input songs. Musical characteristics are extracted from both songs and combined into a single input vector. The "perturbing" step (modifying the input based on user intent) is adjusted to ensure the first song has a greater influence on the final output than the second song. The program extracts a first set of musical characteristics from a first input musical piece; prepares the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; provides the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operates the unsupervised neural net using the perturbed input vector to calculate an output vector; and uses the output vector to create an output musical piece.
16. The method as recited in claim 1 , further comprising: receiving a user request for a plurality of output musical pieces; and using a plurality of output vectors, each output vector from a different higher level within the unsupervised neural net.
The music generation method allows the user to request multiple output musical pieces. Each musical piece is generated using an output vector taken from a different, higher-level layer within the unsupervised neural network, providing different musical characteristics for each output. The system extracts a first set of musical characteristics from a first input musical piece; preparing the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
17. The method as recited in claim 4 , wherein operating the unsupervised neural net using the perturbed input vector trains Restricted Boltzmann Machines using a contrastive divergence process.
When using Restricted Boltzmann Machines (RBMs) in the music generation method, the neural network is trained using a contrastive divergence process. During operation of the network with the perturbed input vector, the RBMs learn from the data through this contrastive divergence training method. Key signatures are associated with the user's chosen intent (mood, genre, etc.) and a rule directs the selection of a set of pitches from that key signature and the system extracts a first set of musical characteristics from a first input musical piece; preparing the first set of musical characteristics as an input vector into an unsupervised neural net comprised of a plurality of computing layers, wherein each computing layer is composed of a set of nodes, and the input vector is prepared by perturbing the first set of musical characteristics according to the user intent expressed in the user input to create a perturbed input vector; providing the perturbed input vector into a first set of nodes in a first visible layer of the unsupervised neural net; operating the unsupervised neural net using the perturbed input vector to calculate an output vector from a higher set of nodes of the unsupervised neural net; and using the output vector to create an output musical piece.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
October 12, 2015
July 25, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.